Agent Incentives: A Causal Perspective
Abstract
We present a framework for analysing agent incentives using causal influence diagrams. We establish that a well-known criterion for value of information is complete. We propose a new graphical criterion for value of control, establishing its soundness and completeness. We also introduce two new concepts for incentive analysis: response incentives indicate which changes in the environment affect an optimal decision, while instrumental control incentives establish whether an agent can influence its utility via a variable X. For both new concepts, we provide sound and complete graphical criteria. We show by example how these results can help with evaluating the safety and fairness of an AI system
Cite
Text
Everitt et al. "Agent Incentives: A Causal Perspective." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I13.17368Markdown
[Everitt et al. "Agent Incentives: A Causal Perspective." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/everitt2021aaai-agent/) doi:10.1609/AAAI.V35I13.17368BibTeX
@inproceedings{everitt2021aaai-agent,
title = {{Agent Incentives: A Causal Perspective}},
author = {Everitt, Tom and Carey, Ryan and Langlois, Eric D. and Ortega, Pedro A. and Legg, Shane},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2021},
pages = {11487-11495},
doi = {10.1609/AAAI.V35I13.17368},
url = {https://mlanthology.org/aaai/2021/everitt2021aaai-agent/}
}